Forecasting Domestic Guest Nights in Ancient Cities of Sri Lanka: Hybrid Approach

Abstract

The Ancient cities are highly occupied by domestic tourists after 2009. The high occupancy increases the demand for accommodation. Hence, the hotel industry should adopt various practices to maximize profits and minimize the risk. This can be achieved by accurate forecasting. But, there were least attempts on forecasting occupancy guest nights of domestic tourist in Ancient Cities of Sri Lankan. Therefore, this study was focused on forecasting occupancy guest nights of domestic tourist in Ancient cities of Sri Lanka. Monthly data of foreign guest nights for the period of January 2008 to December 2016 were obtained from Sri Lanka Tourism Development Authority (SLTDA). The trend models; Linear, Quadratic, Growth Curve and S-Curve models were tested. The Anderson-Darling test revealed the residuals of Linear and Quadratic were normally distributed, but Ljung-Box Q-test and Auto-Correlation Function (ACF) does not confirm the independence. But the residuals of Quadratic and S-Curve models were not normally distributed. Therefore the de-trended data were further analysed; the stationary of the series was tested by Augmented Dickey-Fuller test and ACF. Then the Auto-Regressive Integrated Moving Average (ARIMA) model was tested on each series. The ARIMA model was well fitted for de-trended series of linear trend model and Growth Curve model. Hence, the residuals of two hybrid models; Linear trend-ARIMA and Growth Curve trend-ARIMA models were tested for model assumptions. It was concluded that both Hybrid models; Linear trend-ARIMA and Growth Curve-ARIMA are suitable for forecasting occupancy guest nights of domestic tourist in Ancient Cities of Sri Lanka. The results of this study can be used for strategy and policy development of business, local government authorities of Ancient Cities of Sri Lanka. It is recommended to test the Circular Model; in order to see whether the forecasting ability improves.

Keywords: Trend, ARIMA, Ancient Cities, Occupancy